This paper does not describe a new method; instead, it provides a thorough exploration of an important yet understudied design space related to recent advances in text-to-image synthesis—specifically, the deep fusion of large language models (LLMs) with diffusion transformers (DiTs) for multi-modal generation. Previous studies mainly focused on over-all system performance rather than detailed comparisons with alternative methods, and key design details and training recipes were often left undisclosed. These gaps create uncertainty about the real potential of this approach. To fill these gaps, we conduct an empirical study on text-to-image generation, performing controlled comparisons with established baselines, analyzing important design choices, and providing a clear, reproducible recipe for training at scale. We hope this work offers meaningful data points and practical guidelines for future research in multimodal generation.

Diffusion models build a new milestone for image generation yet raising public concerns, for they can be fine-tuned on unauthorized images for customization. Protection based on adversarial attacks rises to encounter this unauthorized diffusion customization, by adding protective watermarks to images and poisoning diffusion models. However, current protection, leveraging untargeted attacks, does not appear to be effective enough. In this paper, we propose a simple yet effective improvement for the protection against unauthorized diffusion customization by introducing targeted attacks. We show that by carefully selecting the target, targeted attacks significantly outperform untargeted attacks in poisoning diffusion models and degrading the customization image quality. Extensive experiments validate the superiority of our method on two mainstream customization methods of diffusion models, compared to existing protections. To explain the surprising success of targeted attacks, we delve into the mechanism of attack-based protections and propose a hypothesis based on our observation, which enhances the comprehension of attack-based protections. To the best of our knowledge, we are the first to both reveal the vulnerability of diffusion models to targeted attacks and leverage targeted attacks to enhance protection against unauthorized diffusion customization.

With the progress of software technology, vulnerability detection is more important in software security. The mainstream method lacks discriminability and explainability as it uses graph neural network to fuse features simultaneously. Meanwhile only showing the presence of vulnerabilities limits its usefulness. Therefore, we propose BMAAVD, a Vulnerability Detection framework based on Bilateral Masks Aggregate Attention mechanism, including a staged fusion based on feature level with adaptive structures. It treats detection as a multi-classification task and outputs classification information to improve usefulness. BMAAVD performs well on both synthetic and real datasets, achieving an average increase of 7.61 % and 14.82% in F1 score, and the group bagging training strategy we promoted improves the model's performance in data imbalance.